lookml-liquid

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of educational content and LookML code snippets designed to teach developers how to use Liquid variables effectively. All examples follow standard Looker development patterns.
  • [DATA_EXPOSURE]: No hardcoded credentials, sensitive file path access, or unauthorized data exfiltration mechanisms were found. The use of user attributes and filters is documented within the context of standard Looker functionality.
  • [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to bypass safety filters or override system instructions.
  • [REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or execute code from remote sources. It is entirely focused on templating within the Looker platform.
  • [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or privileged operations present in the documentation.
  • [INDIRECT_PROMPT_INJECTION]: While the skill explains how to ingest user-supplied filters and parameters, it provides explicit security guidance to use the | sql_quote filter to prevent SQL injection, demonstrating a security-conscious design.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:06 PM
Security Audit — agent-trust-hub — lookml-liquid